Rotary joint and actuator sensors such as encoders and potentiometers have been the mainstay for sensing and controlling robots and other mechatronic systems for nearly a century. For a given kinematic configuration, joint and actuator positions and their derivatives are used to compute and control robot pose, and to achieve navigation and manipulation tasks. However, the traditional model of robot hardware with heavy, rigid links and joints with tight tolerances is evolving due to needs associated with operation in unstructured and human environments. Compliant/“soft” robot hardware and mechanically-adaptive “underactuated” mechanisms facilitate handling uncertainty, particularly during contact tasks such as manipulation and legged locomotion, as well as assisting with safe operation around humans.
We propose a novel visual servoing method that controls a robotic manipulator in the configuration space as opposed to the classical vision-based control methods solely focusing on the end effector pose. We first extract the robot’s shape from depth images using a skeletonization algorithm and represent it using parametric curves. We then adopt an adaptive visual servoing scheme that estimates the Jacobian online relating the changes of the curve parameters and the joint velocities.
The proposed scheme does not only enable controlling a manipulator in the configuration space, but also demonstrates a better transient response while converging to the goal configuration compared to the classical adaptive visual servoing methods. It also provide superior performance in the control of low stiffness / compliant robots.
We present simulations and real robot experiments that demonstrate the capabilities of the proposed method and analyze its performance, robustness, and repeatability compared to the classical algorithms. The proposed method can assert control over the configuration space of the robot as discussed above. This can be helpful to leverage redundancy in continuum robots.
Skeleton-based Adaptive Visual Servoing for Control of Robotic Manipulators in Configuration Space,
A. Gandhi, S. Chatterjee, B. Calli
IEEE/ RSJ International Conference on Intelligent Robots and Systems, 2022
[Paper] [Video]